Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    following

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     collapse
    -0.07
     Guards
    -0.07
    _z
    -0.07
    啪
    -0.07
     labels
    -0.06
     moves
    -0.06
     robbery
    -0.06
     心
    -0.06
    pection
    -0.06
     crippling
    -0.06
    POSITIVE LOGITS
     Аль
    0.06
     지정
    0.06
    (schema
    0.06
    olleyError
    0.06
    ColorBrush
    0.06
    >Loading
    0.06
    mailbox
    0.06
    bird
    0.06
    (dictionary
    0.06
    NegativeButton
    0.06
    Act Density 0.024%

    No Known Activations